Análisis de modelos SOM - Frecuencia datos de entrada: semana

Modelo

• ID: 145
• Descripción:
• Frecuencia: semana
• Variables: fecha_cnt, tmax, tmin, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-145.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 156652 objects.
Mean distance to the closest unit in the map: 0.874.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_semana_2k.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt          tmax       
 Length:156652      Length:156652      Min.   : 1.00   Min.   :-109.0  
 Class :character   Class :character   1st Qu.:13.00   1st Qu.: 147.0  
 Mode  :character   Mode  :character   Median :27.00   Median : 201.0  
                                       Mean   :26.53   Mean   : 202.1  
                                       3rd Qu.:40.00   3rd Qu.: 262.0  
                                       Max.   :53.00   Max.   : 442.0  
      tmin             precip           nevada    prof_nieve      
 Min.   :-189.00   Min.   :  0.00   Min.   :0   Min.   :   0.000  
 1st Qu.:  48.00   1st Qu.:  0.00   1st Qu.:0   1st Qu.:   0.000  
 Median :  98.00   Median :  3.00   Median :0   Median :   0.000  
 Mean   :  98.13   Mean   : 16.92   Mean   :0   Mean   :   0.604  
 3rd Qu.: 152.00   3rd Qu.: 20.00   3rd Qu.:0   3rd Qu.:   0.000  
 Max.   : 272.00   Max.   :690.00   Max.   :0   Max.   :1073.000  
    longitud        latitud           altitud      
 Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:39.01   1st Qu.: -4.850   1st Qu.:  44.0  
 Median :41.22   Median : -1.411   Median : 263.0  
 Mean   :40.05   Mean   : -2.426   Mean   : 478.5  
 3rd Qu.:42.19   3rd Qu.:  1.272   3rd Qu.: 687.0  
 Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

    1     2     3     4     5     6     7     8     9    10    11    12    13 
 4443 11003  4807  3907  9789  7109  8121  8370  3561  3891  6694  7120  3846 
   14    15    16    17    18    19    20    21    22    23    24    25 
 5155  6460  3593  2318  5366  5832  5614  7946  3693  7323  7109 13582 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

     fecha_cnt      tmax       tmin   longitud    latitud    altitud
[1,] 0.3514805 0.7931994 0.90137087 -0.5066463 -0.2597551 -0.4093813
[2,] 0.7120974 0.1095887 0.09326044  0.4392518  0.4500446  0.1089092

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   latitud fecha_cnt      tmax      tmin   altitud 
0.9601979 0.9279965 0.9259201 0.9178520 0.9037189 0.8873639 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-31.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.:13.00   1st Qu.:152.0   1st Qu.:  52.00   1st Qu.:  0.00   1st Qu.:0  
 Median :26.00   Median :203.0   Median :  99.00   Median :  3.00   Median :0  
 Mean   :26.52   Mean   :208.6   Mean   :  99.42   Mean   : 16.49   Mean   :0  
 3rd Qu.:40.00   3rd Qu.:267.0   3rd Qu.: 149.00   3rd Qu.: 20.00   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   : 272.00   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:39.56   1st Qu.:-4.488   1st Qu.:  52.0  
 Median :  0.00000   Median :41.29   Median :-1.293   Median : 258.0  
 Mean   :  0.06502   Mean   :40.73   Mean   :-1.680   Mean   : 367.1  
 3rd Qu.:  0.00000   3rd Qu.:42.12   3rd Qu.: 1.296   3rd Qu.: 628.0  
 Max.   :299.00000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 14.0   Min.   :-34.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:148.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.31   Mean   :229.6   Mean   :165.2   Mean   :  6.232   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 369.8  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin             precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.00  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.00  
 Median :27.00   Median :  77.00   Median :  10.00   Median : 19.00  
 Mean   :26.83   Mean   :  82.58   Mean   :  12.64   Mean   : 33.69  
 3rd Qu.:40.00   3rd Qu.: 137.00   3rd Qu.:  61.00   3rd Qu.: 48.00  
 Max.   :53.00   Max.   : 263.00   Max.   : 154.00   Max.   :615.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.0544  
 Mean   :0   Mean   :   8.784   Mean   :42.23   Mean   :  0.7367  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1002  
 1st Qu.:1894  
 Median :2230  
 Mean   :2152  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin             precip           nevada 
 Min.   : 1.0   Min.   :-22.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.0   1st Qu.:135.0   1st Qu.:  32.00   1st Qu.:  0.00   1st Qu.:0  
 Median :11.0   Median :170.0   Median :  66.00   Median :  6.00   Median :0  
 Mean   :11.6   Mean   :169.4   Mean   :  64.98   Mean   : 18.59   Mean   :0  
 3rd Qu.:17.0   3rd Qu.:205.0   3rd Qu.:  99.00   3rd Qu.: 25.00   3rd Qu.:0  
 Max.   :31.0   Max.   :323.0   Max.   : 202.00   Max.   :608.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud    
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1  
 1st Qu.:  0.0000   1st Qu.:39.56   1st Qu.:-4.680   1st Qu.:  47  
 Median :  0.0000   Median :41.32   Median :-1.293   Median : 251  
 Mean   :  0.1037   Mean   :40.76   Mean   :-1.686   Mean   : 356  
 3rd Qu.:  0.0000   3rd Qu.:42.18   3rd Qu.: 1.331   3rd Qu.: 617  
 Max.   :299.0000   Max.   :43.57   Max.   : 4.216   Max.   :1572  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 14.0   Min.   :-34.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:148.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.31   Mean   :229.6   Mean   :165.2   Mean   :  6.232   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 369.8  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :14.00   Min.   :-31.0   Min.   :-155.0   Min.   :  0.00   Min.   :0  
 1st Qu.:30.00   1st Qu.:180.0   1st Qu.:  82.0   1st Qu.:  0.00   1st Qu.:0  
 Median :38.00   Median :250.0   Median : 133.0   Median :  2.00   Median :0  
 Mean   :37.46   Mean   :237.4   Mean   : 124.7   Mean   : 14.96   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:296.0   3rd Qu.: 173.0   3rd Qu.: 16.00   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   : 272.0   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:39.56   1st Qu.:-4.127   1st Qu.:  52.0  
 Median :  0.00000   Median :41.22   Median :-1.293   Median : 261.0  
 Mean   :  0.03667   Mean   :40.72   Mean   :-1.675   Mean   : 375.3  
 3rd Qu.:  0.00000   3rd Qu.:42.08   3rd Qu.: 1.201   3rd Qu.: 656.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax              tmin             precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.00  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.00  
 Median :27.00   Median :  77.00   Median :  10.00   Median : 19.00  
 Mean   :26.83   Mean   :  82.58   Mean   :  12.64   Mean   : 33.69  
 3rd Qu.:40.00   3rd Qu.: 137.00   3rd Qu.:  61.00   3rd Qu.: 48.00  
 Max.   :53.00   Max.   : 263.00   Max.   : 154.00   Max.   :615.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.0544  
 Mean   :0   Mean   :   8.784   Mean   :42.23   Mean   :  0.7367  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1002  
 1st Qu.:1894  
 Median :2230  
 Mean   :2152  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin             precip           nevada 
 Min.   : 1.0   Min.   :-22.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.0   1st Qu.:135.0   1st Qu.:  32.00   1st Qu.:  0.00   1st Qu.:0  
 Median :11.0   Median :170.0   Median :  66.00   Median :  6.00   Median :0  
 Mean   :11.6   Mean   :169.4   Mean   :  64.98   Mean   : 18.59   Mean   :0  
 3rd Qu.:17.0   3rd Qu.:205.0   3rd Qu.:  99.00   3rd Qu.: 25.00   3rd Qu.:0  
 Max.   :31.0   Max.   :323.0   Max.   : 202.00   Max.   :608.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud    
 Min.   :  0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1  
 1st Qu.:  0.0000   1st Qu.:39.56   1st Qu.:-4.680   1st Qu.:  47  
 Median :  0.0000   Median :41.32   Median :-1.293   Median : 251  
 Mean   :  0.1037   Mean   :40.76   Mean   :-1.686   Mean   : 356  
 3rd Qu.:  0.0000   3rd Qu.:42.18   3rd Qu.: 1.331   3rd Qu.: 617  
 Max.   :299.0000   Max.   :43.57   Max.   : 4.216   Max.   :1572  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 14.0   Min.   :-34.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:148.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.31   Mean   :229.6   Mean   :165.2   Mean   :  6.232   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 369.8  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :29.00   Min.   :-31.0   Min.   :-155.0   Min.   :  0.00   Min.   :0  
 1st Qu.:44.00   1st Qu.:123.0   1st Qu.:  29.0   1st Qu.:  0.00   1st Qu.:0  
 Median :47.00   Median :157.0   Median :  62.0   Median :  6.00   Median :0  
 Mean   :46.87   Mean   :154.9   Mean   :  58.3   Mean   : 22.19   Mean   :0  
 3rd Qu.:50.00   3rd Qu.:186.0   3rd Qu.:  89.0   3rd Qu.: 28.00   3rd Qu.:0  
 Max.   :53.00   Max.   :297.0   Max.   : 187.0   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.07   1st Qu.:-4.680   1st Qu.:  81.0  
 Median :  0.00000   Median :41.39   Median :-1.863   Median : 412.0  
 Mean   :  0.09416   Mean   :40.84   Mean   :-1.924   Mean   : 438.2  
 3rd Qu.:  0.00000   3rd Qu.:42.23   3rd Qu.: 1.165   3rd Qu.: 735.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :14.00   Min.   :164.0   Min.   : 46.0   Min.   :  0.00   Min.   :0  
 1st Qu.:27.00   1st Qu.:253.0   1st Qu.:134.0   1st Qu.:  0.00   1st Qu.:0  
 Median :32.00   Median :284.0   Median :161.0   Median :  1.00   Median :0  
 Mean   :32.25   Mean   :283.1   Mean   :161.5   Mean   : 10.95   Mean   :0  
 3rd Qu.:37.00   3rd Qu.:312.0   3rd Qu.:188.0   3rd Qu.: 11.00   3rd Qu.:0  
 Max.   :52.00   Max.   :442.0   Max.   :272.0   Max.   :610.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:39.49   1st Qu.:-4.049   1st Qu.:  43.3  
 Median :0.00e+00   Median :41.17   Median :-1.117   Median : 192.0  
 Mean   :4.78e-03   Mean   :40.65   Mean   :-1.538   Mean   : 340.4  
 3rd Qu.:0.00e+00   3rd Qu.:42.00   3rd Qu.: 1.331   3rd Qu.: 611.0  
 Max.   :1.73e+02   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax              tmin             precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.00  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.00  
 Median :27.00   Median :  77.00   Median :  10.00   Median : 19.00  
 Mean   :26.83   Mean   :  82.58   Mean   :  12.64   Mean   : 33.69  
 3rd Qu.:40.00   3rd Qu.: 137.00   3rd Qu.:  61.00   3rd Qu.: 48.00  
 Max.   :53.00   Max.   : 263.00   Max.   : 154.00   Max.   :615.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.0544  
 Mean   :0   Mean   :   8.784   Mean   :42.23   Mean   :  0.7367  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1002  
 1st Qu.:1894  
 Median :2230  
 Mean   :2152  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin            precip          nevada 
 Min.   : 1.0   Min.   : 54.0   Min.   :-33.00   Min.   :  0.0   Min.   :0  
 1st Qu.: 8.0   1st Qu.:159.0   1st Qu.: 57.00   1st Qu.:  0.0   1st Qu.:0  
 Median :14.0   Median :185.0   Median : 81.00   Median :  6.0   Median :0  
 Mean   :13.2   Mean   :187.9   Mean   : 83.32   Mean   : 19.3   Mean   :0  
 3rd Qu.:18.0   3rd Qu.:216.0   3rd Qu.:109.00   3rd Qu.: 26.0   3rd Qu.:0  
 Max.   :31.0   Max.   :323.0   Max.   :202.00   Max.   :523.0   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:38.88   1st Qu.:-5.346   1st Qu.:  32.0  
 Median :  0.00000   Median :41.20   Median :-1.169   Median :  98.0  
 Mean   :  0.03746   Mean   :40.57   Mean   :-1.784   Mean   : 250.4  
 3rd Qu.:  0.00000   3rd Qu.:42.18   3rd Qu.: 1.296   3rd Qu.: 412.0  
 Max.   :164.00000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 14.0   Min.   :-34.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:148.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.31   Mean   :229.6   Mean   :165.2   Mean   :  6.232   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 369.8  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax          tmin             precip          nevada 
 Min.   : 1.000   Min.   :-22   Min.   :-161.00   Min.   :  0.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.: 90   1st Qu.: -11.00   1st Qu.:  0.0   1st Qu.:0  
 Median : 6.000   Median :112   Median :   9.00   Median :  6.0   Median :0  
 Mean   : 6.479   Mean   :110   Mean   :   6.22   Mean   : 16.3   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:132   3rd Qu.:  26.00   3rd Qu.: 21.0   3rd Qu.:0  
 Max.   :28.000   Max.   :209   Max.   :  82.00   Max.   :608.0   Max.   :0  
   prof_nieve          longitud        latitud          altitud    
 Min.   :  0.0000   Min.   :37.16   Min.   :-8.411   Min.   :   2  
 1st Qu.:  0.0000   1st Qu.:40.76   1st Qu.:-3.764   1st Qu.: 513  
 Median :  0.0000   Median :41.63   Median :-1.636   Median : 690  
 Mean   :  0.3157   Mean   :41.37   Mean   :-1.370   Mean   : 694  
 3rd Qu.:  0.0000   3rd Qu.:42.14   3rd Qu.: 1.331   3rd Qu.: 900  
 Max.   :299.0000   Max.   :43.36   Max.   : 4.216   Max.   :1572  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :29.00   Min.   :-31.0   Min.   :-155.0   Min.   :  0.00   Min.   :0  
 1st Qu.:44.00   1st Qu.:123.0   1st Qu.:  29.0   1st Qu.:  0.00   1st Qu.:0  
 Median :47.00   Median :157.0   Median :  62.0   Median :  6.00   Median :0  
 Mean   :46.87   Mean   :154.9   Mean   :  58.3   Mean   : 22.19   Mean   :0  
 3rd Qu.:50.00   3rd Qu.:186.0   3rd Qu.:  89.0   3rd Qu.: 28.00   3rd Qu.:0  
 Max.   :53.00   Max.   :297.0   Max.   : 187.0   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.07   1st Qu.:-4.680   1st Qu.:  81.0  
 Median :  0.00000   Median :41.39   Median :-1.863   Median : 412.0  
 Mean   :  0.09416   Mean   :40.84   Mean   :-1.924   Mean   : 438.2  
 3rd Qu.:  0.00000   3rd Qu.:42.23   3rd Qu.: 1.165   3rd Qu.: 735.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :14.00   Min.   :164.0   Min.   : 46.0   Min.   :  0.00   Min.   :0  
 1st Qu.:27.00   1st Qu.:253.0   1st Qu.:134.0   1st Qu.:  0.00   1st Qu.:0  
 Median :32.00   Median :284.0   Median :161.0   Median :  1.00   Median :0  
 Mean   :32.25   Mean   :283.1   Mean   :161.5   Mean   : 10.95   Mean   :0  
 3rd Qu.:37.00   3rd Qu.:312.0   3rd Qu.:188.0   3rd Qu.: 11.00   3rd Qu.:0  
 Max.   :52.00   Max.   :442.0   Max.   :272.0   Max.   :610.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:39.49   1st Qu.:-4.049   1st Qu.:  43.3  
 Median :0.00e+00   Median :41.17   Median :-1.117   Median : 192.0  
 Mean   :4.78e-03   Mean   :40.65   Mean   :-1.538   Mean   : 340.4  
 3rd Qu.:0.00e+00   3rd Qu.:42.00   3rd Qu.: 1.331   3rd Qu.: 611.0  
 Max.   :1.73e+02   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax              tmin             precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.00  
 1st Qu.:14.00   1st Qu.:  29.00   1st Qu.: -33.00   1st Qu.:  3.00  
 Median :27.00   Median :  77.00   Median :  10.00   Median : 19.00  
 Mean   :26.83   Mean   :  82.58   Mean   :  12.64   Mean   : 33.69  
 3rd Qu.:40.00   3rd Qu.: 137.00   3rd Qu.:  61.00   3rd Qu.: 48.00  
 Max.   :53.00   Max.   : 263.00   Max.   : 154.00   Max.   :615.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.0544  
 Mean   :0   Mean   :   8.784   Mean   :42.23   Mean   :  0.7367  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1002  
 1st Qu.:1894  
 Median :2230  
 Mean   :2152  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 54.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 9.00   1st Qu.:156.0   1st Qu.: 54.00   1st Qu.:  0.00   1st Qu.:0  
 Median :14.00   Median :182.0   Median : 77.00   Median :  7.00   Median :0  
 Mean   :13.57   Mean   :184.9   Mean   : 79.51   Mean   : 20.33   Mean   :0  
 3rd Qu.:19.00   3rd Qu.:213.0   3rd Qu.:103.00   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :31.00   Max.   :322.0   Max.   :187.00   Max.   :523.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :37.79   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.72   1st Qu.:-3.6781   1st Qu.:  43.0  
 Median :  0.00000   Median :41.57   Median : 0.4914   Median : 147.0  
 Mean   :  0.04412   Mean   :41.41   Mean   :-1.0361   Mean   : 284.8  
 3rd Qu.:  0.00000   3rd Qu.:42.37   3rd Qu.: 1.6331   3rd Qu.: 445.0  
 Max.   :164.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 86.0   Min.   :-29.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.00   1st Qu.:170.0   1st Qu.: 71.00   1st Qu.:  0.00   1st Qu.:0  
 Median :12.00   Median :195.0   Median :101.00   Median :  2.00   Median :0  
 Mean   :11.68   Mean   :200.2   Mean   : 98.84   Mean   : 15.12   Mean   :0  
 3rd Qu.:17.00   3rd Qu.:228.0   3rd Qu.:127.00   3rd Qu.: 19.00   3rd Qu.:0  
 Max.   :28.00   Max.   :323.0   Max.   :202.00   Max.   :354.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud     
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.949   Min.   :  1.0  
 1st Qu.: 0.00000   1st Qu.:36.64   1st Qu.:-6.257   1st Qu.: 21.0  
 Median : 0.00000   Median :37.16   Median :-5.598   Median : 47.0  
 Mean   : 0.01033   Mean   :37.12   Mean   :-4.833   Mean   :110.6  
 3rd Qu.: 0.00000   3rd Qu.:37.78   3rd Qu.:-3.789   3rd Qu.: 90.0  
 Max.   :10.00000   Max.   :39.88   Max.   :-0.500   Max.   :717.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 14.0   Min.   :-34.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:148.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.31   Mean   :229.6   Mean   :165.2   Mean   :  6.232   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 369.8  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax          tmin             precip          nevada 
 Min.   : 1.000   Min.   :-22   Min.   :-161.00   Min.   :  0.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.: 90   1st Qu.: -11.00   1st Qu.:  0.0   1st Qu.:0  
 Median : 6.000   Median :112   Median :   9.00   Median :  6.0   Median :0  
 Mean   : 6.479   Mean   :110   Mean   :   6.22   Mean   : 16.3   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:132   3rd Qu.:  26.00   3rd Qu.: 21.0   3rd Qu.:0  
 Max.   :28.000   Max.   :209   Max.   :  82.00   Max.   :608.0   Max.   :0  
   prof_nieve          longitud        latitud          altitud    
 Min.   :  0.0000   Min.   :37.16   Min.   :-8.411   Min.   :   2  
 1st Qu.:  0.0000   1st Qu.:40.76   1st Qu.:-3.764   1st Qu.: 513  
 Median :  0.0000   Median :41.63   Median :-1.636   Median : 690  
 Mean   :  0.3157   Mean   :41.37   Mean   :-1.370   Mean   : 694  
 3rd Qu.:  0.0000   3rd Qu.:42.14   3rd Qu.: 1.331   3rd Qu.: 900  
 Max.   :299.0000   Max.   :43.36   Max.   : 4.216   Max.   :1572  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :29.00   Min.   :-31.0   Min.   :-155.0   Min.   :  0.00   Min.   :0  
 1st Qu.:44.00   1st Qu.:123.0   1st Qu.:  29.0   1st Qu.:  0.00   1st Qu.:0  
 Median :47.00   Median :157.0   Median :  62.0   Median :  6.00   Median :0  
 Mean   :46.87   Mean   :154.9   Mean   :  58.3   Mean   : 22.19   Mean   :0  
 3rd Qu.:50.00   3rd Qu.:186.0   3rd Qu.:  89.0   3rd Qu.: 28.00   3rd Qu.:0  
 Max.   :53.00   Max.   :297.0   Max.   : 187.0   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.07   1st Qu.:-4.680   1st Qu.:  81.0  
 Median :  0.00000   Median :41.39   Median :-1.863   Median : 412.0  
 Mean   :  0.09416   Mean   :40.84   Mean   :-1.924   Mean   : 438.2  
 3rd Qu.:  0.00000   3rd Qu.:42.23   3rd Qu.: 1.165   3rd Qu.: 735.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :14.00   Min.   :164.0   Min.   : 46.0   Min.   :  0.00   Min.   :0  
 1st Qu.:27.00   1st Qu.:253.0   1st Qu.:134.0   1st Qu.:  0.00   1st Qu.:0  
 Median :32.00   Median :284.0   Median :161.0   Median :  1.00   Median :0  
 Mean   :32.25   Mean   :283.1   Mean   :161.5   Mean   : 10.95   Mean   :0  
 3rd Qu.:37.00   3rd Qu.:312.0   3rd Qu.:188.0   3rd Qu.: 11.00   3rd Qu.:0  
 Max.   :52.00   Max.   :442.0   Max.   :272.0   Max.   :610.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:39.49   1st Qu.:-4.049   1st Qu.:  43.3  
 Median :0.00e+00   Median :41.17   Median :-1.117   Median : 192.0  
 Mean   :4.78e-03   Mean   :40.65   Mean   :-1.538   Mean   : 340.4  
 3rd Qu.:0.00e+00   3rd Qu.:42.00   3rd Qu.: 1.331   3rd Qu.: 611.0  
 Max.   :1.73e+02   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-79.0   Min.   :-146.00   Min.   :  0.00   Min.   :0  
 1st Qu.:28.00   1st Qu.: 66.0   1st Qu.:   6.00   1st Qu.:  2.00   1st Qu.:0  
 Median :37.00   Median :120.0   Median :  48.00   Median : 16.00   Median :0  
 Mean   :36.31   Mean   :112.7   Mean   :  40.82   Mean   : 30.67   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:160.2   3rd Qu.:  81.00   3rd Qu.: 42.00   3rd Qu.:0  
 Max.   :53.00   Max.   :263.0   Max.   : 154.00   Max.   :459.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud    
 Min.   :  0.000   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:  0.000   1st Qu.:42.18   1st Qu.: 0.7317   1st Qu.:1894  
 Median :  0.000   Median :42.47   Median : 1.0544   Median :2230  
 Mean   :  2.256   Mean   :42.22   Mean   : 0.7342   Mean   :2133  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.: 1.7150   3rd Qu.:2400  
 Max.   :805.000   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax              tmin             precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.00  
 1st Qu.: 5.00   1st Qu.:   4.00   1st Qu.: -60.00   1st Qu.:  6.00  
 Median :10.00   Median :  34.00   Median : -31.00   Median : 25.00  
 Mean   :10.56   Mean   :  30.98   Mean   : -35.71   Mean   : 38.85  
 3rd Qu.:15.00   3rd Qu.:  62.00   3rd Qu.:  -7.00   3rd Qu.: 55.00  
 Max.   :25.00   Max.   : 132.00   Max.   :  56.00   Max.   :615.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.00   Median :42.47   Median :  1.0544  
 Mean   :0   Mean   :  19.98   Mean   :42.25   Mean   :  0.7410  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.00   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1002  
 1st Qu.:1971  
 Median :2247  
 Mean   :2186  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 54.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 7.00   1st Qu.:134.0   1st Qu.: 56.00   1st Qu.:  5.00   1st Qu.:0  
 Median :12.00   Median :159.0   Median : 80.00   Median : 21.00   Median :0  
 Mean   :12.45   Mean   :161.8   Mean   : 78.26   Mean   : 34.75   Mean   :0  
 3rd Qu.:18.00   3rd Qu.:189.0   3rd Qu.:102.00   3rd Qu.: 48.00   3rd Qu.:0  
 Max.   :29.00   Max.   :289.0   Max.   :160.00   Max.   :496.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud     
 Min.   :  0.0000   Min.   :39.47   Min.   :-8.624   Min.   :  4.0  
 1st Qu.:  0.0000   1st Qu.:42.56   1st Qu.:-8.411   1st Qu.: 52.0  
 Median :  0.0000   Median :43.31   Median :-6.044   Median :127.0  
 Mean   :  0.1253   Mean   :43.06   Mean   :-6.062   Mean   :187.3  
 3rd Qu.:  0.0000   3rd Qu.:43.43   3rd Qu.:-3.831   3rd Qu.:336.0  
 Max.   :154.0000   Max.   :43.57   Max.   :-1.636   Max.   :775.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt         tmax            tmin            precip           nevada 
 Min.   : 1.0   Min.   : 90.0   Min.   :-29.00   Min.   :  0.00   Min.   :0  
 1st Qu.:10.0   1st Qu.:164.0   1st Qu.: 54.00   1st Qu.:  0.00   1st Qu.:0  
 Median :15.0   Median :188.0   Median : 76.00   Median :  5.00   Median :0  
 Mean   :13.9   Mean   :191.7   Mean   : 79.87   Mean   : 16.14   Mean   :0  
 3rd Qu.:19.0   3rd Qu.:219.0   3rd Qu.:103.00   3rd Qu.: 21.00   3rd Qu.:0  
 Max.   :31.0   Max.   :322.0   Max.   :187.00   Max.   :523.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :37.79   Min.   :-5.7333   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.35   1st Qu.:-0.5000   1st Qu.:  35.0  
 Median :  0.00000   Median :41.22   Median : 0.8031   Median : 176.0  
 Mean   :  0.02048   Mean   :40.93   Mean   : 0.4271   Mean   : 313.1  
 3rd Qu.:  0.00000   3rd Qu.:41.68   3rd Qu.: 2.0692   3rd Qu.: 541.0  
 Max.   :164.00000   Max.   :43.36   Max.   : 4.2156   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 86.0   Min.   :-29.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.00   1st Qu.:170.0   1st Qu.: 71.00   1st Qu.:  0.00   1st Qu.:0  
 Median :12.00   Median :195.0   Median :101.00   Median :  2.00   Median :0  
 Mean   :11.68   Mean   :200.2   Mean   : 98.84   Mean   : 15.12   Mean   :0  
 3rd Qu.:17.00   3rd Qu.:228.0   3rd Qu.:127.00   3rd Qu.: 19.00   3rd Qu.:0  
 Max.   :28.00   Max.   :323.0   Max.   :202.00   Max.   :354.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud     
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.949   Min.   :  1.0  
 1st Qu.: 0.00000   1st Qu.:36.64   1st Qu.:-6.257   1st Qu.: 21.0  
 Median : 0.00000   Median :37.16   Median :-5.598   Median : 47.0  
 Mean   : 0.01033   Mean   :37.12   Mean   :-4.833   Mean   :110.6  
 3rd Qu.: 0.00000   3rd Qu.:37.78   3rd Qu.:-3.789   3rd Qu.: 90.0  
 Max.   :10.00000   Max.   :39.88   Max.   :-0.500   Max.   :717.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 14.0   Min.   :-34.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:148.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.31   Mean   :229.6   Mean   :165.2   Mean   :  6.232   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :490.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.04   Mean   : 369.8  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax          tmin             precip          nevada 
 Min.   : 1.000   Min.   :-22   Min.   :-161.00   Min.   :  0.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.: 90   1st Qu.: -11.00   1st Qu.:  0.0   1st Qu.:0  
 Median : 6.000   Median :112   Median :   9.00   Median :  6.0   Median :0  
 Mean   : 6.479   Mean   :110   Mean   :   6.22   Mean   : 16.3   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:132   3rd Qu.:  26.00   3rd Qu.: 21.0   3rd Qu.:0  
 Max.   :28.000   Max.   :209   Max.   :  82.00   Max.   :608.0   Max.   :0  
   prof_nieve          longitud        latitud          altitud    
 Min.   :  0.0000   Min.   :37.16   Min.   :-8.411   Min.   :   2  
 1st Qu.:  0.0000   1st Qu.:40.76   1st Qu.:-3.764   1st Qu.: 513  
 Median :  0.0000   Median :41.63   Median :-1.636   Median : 690  
 Mean   :  0.3157   Mean   :41.37   Mean   :-1.370   Mean   : 694  
 3rd Qu.:  0.0000   3rd Qu.:42.14   3rd Qu.: 1.331   3rd Qu.: 900  
 Max.   :299.0000   Max.   :43.36   Max.   : 4.216   Max.   :1572  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :29.00   Min.   :-31.0   Min.   :-155.0   Min.   :  0.00   Min.   :0  
 1st Qu.:44.00   1st Qu.:123.0   1st Qu.:  29.0   1st Qu.:  0.00   1st Qu.:0  
 Median :47.00   Median :157.0   Median :  62.0   Median :  6.00   Median :0  
 Mean   :46.87   Mean   :154.9   Mean   :  58.3   Mean   : 22.19   Mean   :0  
 3rd Qu.:50.00   3rd Qu.:186.0   3rd Qu.:  89.0   3rd Qu.: 28.00   3rd Qu.:0  
 Max.   :53.00   Max.   :297.0   Max.   : 187.0   Max.   :690.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.07   1st Qu.:-4.680   1st Qu.:  81.0  
 Median :  0.00000   Median :41.39   Median :-1.863   Median : 412.0  
 Mean   :  0.09416   Mean   :40.84   Mean   :-1.924   Mean   : 438.2  
 3rd Qu.:  0.00000   3rd Qu.:42.23   3rd Qu.: 1.165   3rd Qu.: 735.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :14.00   Min.   :172.0   Min.   : 46.0   Min.   :  0.00   Min.   :0  
 1st Qu.:26.00   1st Qu.:246.0   1st Qu.:123.0   1st Qu.:  0.00   1st Qu.:0  
 Median :31.00   Median :277.0   Median :143.0   Median :  2.00   Median :0  
 Mean   :30.62   Mean   :278.6   Mean   :143.2   Mean   : 11.54   Mean   :0  
 3rd Qu.:35.00   3rd Qu.:309.0   3rd Qu.:162.0   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :51.00   Max.   :428.0   Max.   :266.0   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :0.00e+00   Min.   :37.13   Min.   :-8.624   Min.   :   4.0  
 1st Qu.:0.00e+00   1st Qu.:40.48   1st Qu.:-5.498   1st Qu.: 405.0  
 Median :0.00e+00   Median :41.77   Median :-3.678   Median : 626.0  
 Mean   :9.23e-03   Mean   :41.52   Mean   :-3.079   Mean   : 598.2  
 3rd Qu.:0.00e+00   3rd Qu.:42.56   3rd Qu.:-1.411   3rd Qu.: 816.0  
 Max.   :1.73e+02   Max.   :43.57   Max.   : 2.482   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-79.0   Min.   :-146.00   Min.   :  0.00   Min.   :0  
 1st Qu.:28.00   1st Qu.: 66.0   1st Qu.:   6.00   1st Qu.:  2.00   1st Qu.:0  
 Median :37.00   Median :120.0   Median :  48.00   Median : 16.00   Median :0  
 Mean   :36.31   Mean   :112.7   Mean   :  40.82   Mean   : 30.67   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:160.2   3rd Qu.:  81.00   3rd Qu.: 42.00   3rd Qu.:0  
 Max.   :53.00   Max.   :263.0   Max.   : 154.00   Max.   :459.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud    
 Min.   :  0.000   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:  0.000   1st Qu.:42.18   1st Qu.: 0.7317   1st Qu.:1894  
 Median :  0.000   Median :42.47   Median : 1.0544   Median :2230  
 Mean   :  2.256   Mean   :42.22   Mean   : 0.7342   Mean   :2133  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.: 1.7150   3rd Qu.:2400  
 Max.   :805.000   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :18.00   Min.   :164.0   Min.   : 73.0   Min.   :  0.00   Min.   :0  
 1st Qu.:28.00   1st Qu.:261.0   1st Qu.:157.0   1st Qu.:  0.00   1st Qu.:0  
 Median :34.00   Median :289.0   Median :181.0   Median :  0.00   Median :0  
 Mean   :33.66   Mean   :287.1   Mean   :177.5   Mean   : 10.43   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:314.0   3rd Qu.:202.0   3rd Qu.:  7.00   3rd Qu.:0  
 Max.   :52.00   Max.   :442.0   Max.   :272.0   Max.   :610.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud     
 Min.   :0.000000   Min.   :35.28   Min.   :-6.9492   Min.   :  1.0  
 1st Qu.:0.000000   1st Qu.:38.00   1st Qu.:-1.1692   1st Qu.: 21.0  
 Median :0.000000   Median :40.82   Median : 0.6319   Median : 68.6  
 Mean   :0.000884   Mean   :39.88   Mean   :-0.1911   Mean   :115.1  
 3rd Qu.:0.000000   3rd Qu.:41.53   3rd Qu.: 1.9356   3rd Qu.:176.0  
 Max.   :6.000000   Max.   :43.36   Max.   : 4.2156   Max.   :691.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax              tmin             precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.00   Min.   :  0.00  
 1st Qu.: 5.00   1st Qu.:   4.00   1st Qu.: -60.00   1st Qu.:  6.00  
 Median :10.00   Median :  34.00   Median : -31.00   Median : 25.00  
 Mean   :10.56   Mean   :  30.98   Mean   : -35.71   Mean   : 38.85  
 3rd Qu.:15.00   3rd Qu.:  62.00   3rd Qu.:  -7.00   3rd Qu.: 55.00  
 Max.   :25.00   Max.   : 132.00   Max.   :  56.00   Max.   :615.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.00   Median :42.47   Median :  1.0544  
 Mean   :0   Mean   :  19.98   Mean   :42.25   Mean   :  0.7410  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.00   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   :1002  
 1st Qu.:1971  
 Median :2247  
 Mean   :2186  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)